Text-to-speech enriching system

• US 10,741,168 B1
• Filed: 10/31/2019
• Issued: 08/11/2020
• Est. Priority Date: 10/31/2019
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Rafferty, Galen, Farivar, Reza, Truong, Anh, Goodsitt, Jeremy, Pham, Vincent, Walters, Austin
• Primary Examiner(s): Han, Qi
• Application Number:
  US16/669,774
• Time in Patent Office: 285 Days
• Field of Search: 704257, 704260, 704270, 7042701, 704272, 704278
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

Disclosed herein are system, method, and computer program product embodiments for a text-to-speech system. An embodiment operates by identifying a document including text, wherein the text includes both a structured portion of text, and an unstructured portion of text. Both the structured portion and unstructured portions of the text are identified within the document rich data, wherein the structured portion corresponds to a rich data portion that includes both a descriptor and content, and wherein an unstructured portion of the text includes alphanumeric text. A summary of the content of the rich data portion of the document at a specified level of detail is generated at a specified level of detail. An audible version of the document including both the text-only portion of the document and the summary of the content of the rich data portion of the document is output.

Claims

1. A computer-implemented method for producing an audible version of a document comprising:

identifying a document including both a rich data portion of content, and an unstructured portion of content;

identifying, within the document, the rich data portion of content that corresponds to a pre-determined format, wherein the rich data portion of content is to be replaced with a summary of the content in the audible version of the document;

determining that the unstructured portion of the document includes alphanumeric text;

generating the summary of the rich data portion of content at a first level of detail based at least in part on a first portion of metadata associated with the rich data portion of content, wherein a second level of detail corresponds to a second portion of the metadata associated with the rich data portion of the content; and

audibly outputting the audible version of the document including both the alphanumeric text of the unstructured portion of the document and the generated summary, wherein the generated summary replaces the rich data portion content from the identified document in the output audible version of the document.

2. The method of claim 1, wherein the rich data portion includes a link to a linked document, and wherein a summary of the linked document is generated based on metadata associated with the linked document.

3. The method of claim 1, further comprising:

generating a second summary of the rich data portion of content at the second level of detail.

4. The method of claim 3, further comprising:

receiving, after the audibly outputting, a request for the second level of detail; and

audibly outputting the second summary responsive to the request for the second level of detail.

5. The method of claim 1, wherein the rich data portion includes a set of statistics.

6. The method of claim 5, wherein the summary for the set of statistics includes a first level of detail summary and a second level of detail summary, wherein the first level of detail corresponds to user preferences for a first user, and wherein the second level of detail corresponds to user preferences for a second user.

7. The method of claim 1, wherein the rich data portion includes an image, and wherein the summary includes one or more identified objects in the image.

8. A system comprising:

a memory; and

at least one processor coupled to the memory and configured to perform operations comprising;

identifying a document including both a rich data portion of content, and an unstructured portion of content;

identifying, within the document, the rich data portion of content that corresponds to a pre-determined format, wherein the rich data portion of content is to be replaced with a summary of the content in the audible version of the document;

determining that the unstructured portion of the document includes alphanumeric text;

generating the summary of the rich data portion of content at a first level of detail based at least in part on a first portion of metadata associated with the rich data portion of content, wherein a second level of detail corresponds to a second portion of the metadata associated with the rich data portion of the content; and

audibly outputting the audible version of the document including both the alphanumeric text of the unstructured portion of the document and the generated summary, wherein the generated summary replaces the rich data portion content from the identified document in the output audible version of the document.

9. The system of claim 8, wherein the rich data portion includes a link to a linked document, and wherein a summary of the linked document is generated based on metadata associated with the linked document.

10. The system of claim 8, the operations further comprising:

generating a second summary of the rich data portion of content at the second level of detail.

11. The system of claim 10, the operations further comprising:

receiving, after the audibly outputting, a request for the second level of detail; and

audibly outputting the second summary responsive to the request for the second level of detail.

12. The system of claim 8, wherein the rich data portion includes a set of statistics.

13. The system of claim 12, wherein the summary for the set of statistics includes a first level of detail summary and a second level of detail summary, wherein the first level of detail corresponds to user preferences for a first user, and wherein the second level of detail corresponds to user preferences for a second user.

14. The system of claim 8, wherein the rich data portion includes an image, and wherein the summary includes one or more identified objects in the image.

15. A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:

identifying a document including both a rich data portion of content, and an unstructured portion of content;

identifying, within the document, the rich data portion of content that corresponds to a pre-determined format, wherein the rich data portion of content is to be replaced with a summary of the content in the audible version of the document;

determining that the unstructured portion of the document includes alphanumeric text;

generating the summary of the rich data portion of content at a first level of detail based at least in part on a first portion of metadata associated with the rich data portion of content, wherein a second level of detail corresponds to a second portion of the metadata associated with the rich data portion of the content; and

audibly outputting the audible version of the document including both the alphanumeric text of the unstructured portion of the document and the generated summary, wherein the generated summary replaces the rich data portion content from the identified document in the output audible version of the document.

16. The device of claim 15, wherein the rich data portion includes a link to a linked document, and wherein a summary of the linked document is generated based on metadata associated with the linked document.

17. The device of claim 15, the operations further comprising:

generating a second summary of the rich data portion of content at the second level of detail.

18. The device of claim 17, the operations further comprising:

receiving, after the audibly outputting, a request for the second level of detail; and

audibly outputting the second summary responsive to the request for the second level of detail.

19. The device of claim 15, wherein the rich data portion includes a set of statistics.

20. The device of claim 19, wherein the summary for the set of statistics includes a first level of detail summary and a second level of detail summary, wherein the first level of detail corresponds to user preferences for a first user, and wherein the second level of detail corresponds to user preferences for a second user.